Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1826. Min Act: -0.0000

Data Index: 55897 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0000

Data Index: 376089 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1777. Min Act: -0.0000

Data Index: 364018 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1725. Min Act: -0.0000

Data Index: 546830 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1668. Min Act: -0.0000

Data Index: 139532 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1681. Min Act: -0.0000

Data Index: 271521 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1723. Min Act: -0.0000

Data Index: 334680 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1661. Min Act: -0.0000

Data Index: 496281 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1621. Min Act: -0.0000

Data Index: 233333 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1546. Min Act: -0.0000

Data Index: 236797 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1453. Min Act: -0.0000

Data Index: 610299 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1538. Min Act: -0.0000

Data Index: 652313 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1485. Min Act: -0.0000

Data Index: 611968 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1603. Min Act: -0.0000

Data Index: 992415 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1439. Min Act: -0.0000

Data Index: 136332 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1433. Min Act: -0.0000

Data Index: 752392 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1491. Min Act: -0.0000

Data Index: 784640 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1379. Min Act: -0.0000

Data Index: 845350 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1408. Min Act: -0.0000

Data Index: 828153 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1017332 (C4 (Web Text))

Max Activating Token Index: 37